linux.git/arch/x86/kernel/kvmclock.c, branch v5.12

KVM: kvmclock: Fix vCPUs > 64 can't be online/hotpluged

2021-03-12T18:18:16+00:00

# lscpu
Architecture:          x86_64
CPU op-mode(s):        32-bit, 64-bit
Byte Order:            Little Endian
CPU(s):                88
On-line CPU(s) list:   0-63
Off-line CPU(s) list:  64-87

# cat /proc/cmdline
BOOT_IMAGE=/vmlinuz-5.10.0-rc3-tlinux2-0050+ root=/dev/mapper/cl-root ro
rd.lvm.lv=cl/root rhgb quiet console=ttyS0 LANG=en_US .UTF-8 no-kvmclock-vsyscall

# echo 1 > /sys/devices/system/cpu/cpu76/online
-bash: echo: write error: Cannot allocate memory

The per-cpu vsyscall pvclock data pointer assigns either an element of the
static array hv_clock_boot (#vCPU <= 64) or dynamically allocated memory
hvclock_mem (vCPU > 64), the dynamically memory will not be allocated if
kvmclock vsyscall is disabled, this can result in cpu hotpluged fails in
kvmclock_setup_percpu() which returns -ENOMEM. It's broken for no-vsyscall
and sometimes you end up with vsyscall disabled if the host does something
strange. This patch fixes it by allocating this dynamically memory
unconditionally even if vsyscall is disabled.

Fixes: 6a1cac56f4 ("x86/kvm: Use __bss_decrypted attribute in shared variables")
Reported-by: Zelin Deng 
Cc: Brijesh Singh 
Cc: stable@vger.kernel.org#v4.19-rc5+
Signed-off-by: Wanpeng Li 
Message-Id: <1614130683-24137-1-git-send-email-wanpengli@tencent.com>
Signed-off-by: Paolo Bonzini

x86/kvm: remove unused macro HV_CLOCK_SIZE

2020-11-16T18:14:21+00:00

This macro is useless, and could cause gcc warning:
arch/x86/kernel/kvmclock.c:47:0: warning: macro "HV_CLOCK_SIZE" is not
used [-Wunused-macros]
Let's remove it.

Signed-off-by: Alex Shi 
Cc: Paolo Bonzini 
Cc: Sean Christopherson 
Cc: Vitaly Kuznetsov 
Cc: Wanpeng Li 
Cc: Jim Mattson 
Cc: Joerg Roedel 
Cc: Thomas Gleixner 
Cc: Ingo Molnar 
Cc: Borislav Petkov 
Cc: x86@kernel.org
Cc: "H. Peter Anvin" 
Cc: kvm@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Message-Id: <1604651963-10067-1-git-send-email-alex.shi@linux.alibaba.com>
Signed-off-by: Paolo Bonzini

x86/vdso: Use generic VDSO clock mode storage

2020-02-17T13:40:23+00:00

Switch to the generic VDSO clock mode storage.

Signed-off-by: Thomas Gleixner 
Reviewed-by: Vincenzo Frascino  (VDSO parts)
Acked-by: Juergen Gross  (Xen parts)
Acked-by: Paolo Bonzini  (KVM parts)
Link: https://lkml.kernel.org/r/20200207124403.152039903@linutronix.de

x86/vdso: Move VDSO clocksource state tracking to callback

2020-02-17T13:40:22+00:00

All architectures which use the generic VDSO code have their own storage
for the VDSO clock mode. That's pointless and just requires duplicate code.

X86 abuses the function which retrieves the architecture specific clock
mode storage to mark the clocksource as used in the VDSO. That's silly
because this is invoked on every tick when the VDSO data is updated.

Move this functionality to the clocksource::enable() callback so it gets
invoked once when the clocksource is installed. This allows to make the
clock mode storage generic.

Signed-off-by: Thomas Gleixner 
Reviewed-by: Michael Kelley   (Hyper-V parts)
Reviewed-by: Vincenzo Frascino  (VDSO parts)
Acked-by: Juergen Gross  (Xen parts)
Link: https://lkml.kernel.org/r/20200207124402.934519777@linutronix.de

x86: kvmguest: use TSC clocksource if invariant TSC is exposed

2019-02-20T21:48:52+00:00

The invariant TSC bit has the following meaning:

"The time stamp counter in newer processors may support an enhancement,
referred to as invariant TSC. Processor's support for invariant TSC
is indicated by CPUID.80000007H:EDX[8]. The invariant TSC will run
at a constant rate in all ACPI P-, C-. and T-states. This is the
architectural behavior moving forward. On processors with invariant TSC
support, the OS may use the TSC for wall clock timer services (instead
of ACPI or HPET timers). TSC reads are much more efficient and do not
incur the overhead associated with a ring transition or access to a
platform resource."

IOW, TSC does not change frequency. In such case, and with
TSC scaling hardware available to handle migration, it is possible
to use the TSC clocksource directly, whose system calls are
faster.

Reduce the rating of kvmclock clocksource to allow TSC clocksource
to be the default if invariant TSC is exposed.

Signed-off-by: Marcelo Tosatti 

v2: Use feature bits and tsc_unstable() check (Sean Christopherson)
Signed-off-by: Paolo Bonzini

x86/kvmclock: set offset for kvm unstable clock

2019-02-20T21:48:19+00:00

VMs may show incorrect uptime and dmesg printk offsets on hypervisors with
unstable clock. The problem is produced when VM is rebooted without exiting
from qemu.

The fix is to calculate clock offset not only for stable clock but for
unstable clock as well, and use kvm_sched_clock_read() which substracts
the offset for both clocks.

This is safe, because pvclock_clocksource_read() does the right thing and
makes sure that clock always goes forward, so once offset is calculated
with unstable clock, we won't get new reads that are smaller than offset,
and thus won't get negative results.

Thank you Jon DeVree for helping to reproduce this issue.

Fixes: 857baa87b642 ("sched/clock: Enable sched clock early")
Cc: stable@vger.kernel.org
Reported-by: Dominique Martinet 
Signed-off-by: Pavel Tatashin 
Signed-off-by: Paolo Bonzini

x86/kvmclock: convert to SPDX identifiers

2018-12-21T10:28:25+00:00

Update the verbose license text with the matching SPDX
license identifier.

Signed-off-by: Peng Hao 
[Changed deprecated GPL-2.0+ to GPL-2.0-or-later. - Radim]
Signed-off-by: Radim Krčmář

Merge branch 'x86-paravirt-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

2018-10-23T16:54:58+00:00

Pull x86 paravirt updates from Ingo Molnar:
 "Two main changes:

   - Remove no longer used parts of the paravirt infrastructure and put
     large quantities of paravirt ops under a new config option
     PARAVIRT_XXL=y, which is selected by XEN_PV only. (Joergen Gross)

   - Enable PV spinlocks on Hyperv (Yi Sun)"

* 'x86-paravirt-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/hyperv: Enable PV qspinlock for Hyper-V
  x86/hyperv: Add GUEST_IDLE_MSR support
  x86/paravirt: Clean up native_patch()
  x86/paravirt: Prevent redefinition of SAVE_FLAGS macro
  x86/xen: Make xen_reservation_lock static
  x86/paravirt: Remove unneeded mmu related paravirt ops bits
  x86/paravirt: Move the Xen-only pv_mmu_ops under the PARAVIRT_XXL umbrella
  x86/paravirt: Move the pv_irq_ops under the PARAVIRT_XXL umbrella
  x86/paravirt: Move the Xen-only pv_cpu_ops under the PARAVIRT_XXL umbrella
  x86/paravirt: Move items in pv_info under PARAVIRT_XXL umbrella
  x86/paravirt: Introduce new config option PARAVIRT_XXL
  x86/paravirt: Remove unused paravirt bits
  x86/paravirt: Use a single ops structure
  x86/paravirt: Remove clobbers from struct paravirt_patch_site
  x86/paravirt: Remove clobbers parameter from paravirt patch functions
  x86/paravirt: Make paravirt_patch_call() and paravirt_patch_jmp() static
  x86/xen: Add SPDX identifier in arch/x86/xen files
  x86/xen: Link platform-pci-unplug.o only if CONFIG_XEN_PVHVM
  x86/xen: Move pv specific parts of arch/x86/xen/mmu.c to mmu_pv.c
  x86/xen: Move pv irq related functions under CONFIG_XEN_PV umbrella

x86/kvm: Use __bss_decrypted attribute in shared variables

2018-09-15T18:48:46+00:00

The recent removal of the memblock dependency from kvmclock caused a SEV
guest regression because the wall_clock and hv_clock_boot variables are
no longer mapped decrypted when SEV is active.

Use the __bss_decrypted attribute to put the static wall_clock and
hv_clock_boot in the .bss..decrypted section so that they are mapped
decrypted during boot.

In the preparatory stage of CPU hotplug, the per-cpu pvclock data pointer
assigns either an element of the static array or dynamically allocated
memory for the pvclock data pointer. The static array are now mapped
decrypted but the dynamically allocated memory is not mapped decrypted.
However, when SEV is active this memory range must be mapped decrypted.

Add a function which is called after the page allocator is up, and
allocate memory for the pvclock data pointers for the all possible cpus.
Map this memory range as decrypted when SEV is active.

Fixes: 368a540e0232 ("x86/kvmclock: Remove memblock dependency")
Suggested-by: Thomas Gleixner 
Signed-off-by: Brijesh Singh 
Signed-off-by: Thomas Gleixner 
Cc: Tom Lendacky 
Cc: Borislav Petkov 
Cc: "H. Peter Anvin" 
Cc: Paolo Bonzini 
Cc: Sean Christopherson 
Cc: "Radim Krčmář" 
Cc: kvm@vger.kernel.org
Link: https://lkml.kernel.org/r/1536932759-12905-3-git-send-email-brijesh.singh@amd.com

x86/paravirt: Use a single ops structure

2018-09-03T14:50:35+00:00

Instead of using six globally visible paravirt ops structures combine
them in a single structure, keeping the original structures as
sub-structures.

This avoids the need to assemble struct paravirt_patch_template at
runtime on the stack each time apply_paravirt() is being called (i.e.
when loading a module).

[ tglx: Made the struct and the initializer tabular for readability sake ]

Signed-off-by: Juergen Gross 
Signed-off-by: Thomas Gleixner 
Cc: xen-devel@lists.xenproject.org
Cc: virtualization@lists.linux-foundation.org
Cc: akataria@vmware.com
Cc: rusty@rustcorp.com.au
Cc: boris.ostrovsky@oracle.com
Cc: hpa@zytor.com
Link: https://lkml.kernel.org/r/20180828074026.820-9-jgross@suse.com